fireworks_delete_deploymentDELETES (shuts down) a Fireworks deployment — stops serving that model and stops its billing. Destructive. Control-plane: DELETE /v1/accounts/{account_id}/deployments/{deployment_id}.
| Name | Required | Description | Default |
|---|---|---|---|
| account_id | No | Fireworks account id. Overrides FIREWORKS_ACCOUNT_ID for this call. | |
| deployment_id | Yes | Deployment id to delete (the resource segment). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotation destructieveHint=true, the description adds specific behavioral details: it 'shuts down' the deployment, stops billing, and includes the HTTP method and path. This provides context that the annotation alone does not offer, earning a score above baseline.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: one sentence conveying the action, effect, destructiveness, and API endpoint. Every word adds value with no redundancy. The key information is front-loaded with the capital 'DELETES', ensuring immediate clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's destructive nature, the description adequately covers the action, consequences, and the HTTP mapping. There is no output schema, but that is typical for delete operations. The description is sufficient for an agent to understand the tool's complete effect without needing additional context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for both parameters. The description does not add new meaning beyond the schema; it mentions the HTTP path but does not clarify the parameters' roles or formats. Thus, the description adds no additional semantic value, resulting in the baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'DELETES', the resource 'Fireworks deployment', and the effects 'stops serving that model and stops its billing'. It distinguishes itself from sibling tools that perform get, list, or create actions, leaving no ambiguity about the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description labels the tool as 'Destructive' and explains the consequences of deletion, but it does not provide explicit guidance on when to use it versus alternatives or state any prerequisites. While the destructive nature is clear, the description lacks explicit when-not-to-use criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct resource and action combination (e.g., create_dataset vs delete_deployment vs list_models), with no overlapping purposes. Descriptions clearly differentiate each tool.
All tools follow a consistent 'fireworks_verb_noun' pattern, with verbs like create, delete, get, list and singular or plural nouns as appropriate. No mixing of conventions.
14 tools cover the main resources of the Fireworks platform (accounts, datasets, deployments, fine-tuning jobs, models, batch inference, users). The scope is appropriate and not overwhelming.
The tool set is heavily read-oriented with only one creation tool (create_dataset) and one deletion tool (delete_deployment). Missing create for deployments, fine-tuning jobs, models; missing update and delete for most resources. Gaps would hinder full workflow automation.